3 papers
cs.CY2026
Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
Charvi Rastogi, Mukul Bhutani, Minsuk Kahng +13
Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for t…
cs.CL2024
Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs
Claire Jin, Sudha Rao, Xiangyu Peng +4
Advancements in large language models (LLMs) are revolutionizing interactive game design, enabling dynamic plotlines and interactions between players and non-player characters (NPC…
cs.CL2024
Player-Driven Emergence in LLM-Driven Game Narrative
Xiangyu Peng, Jessica Quaye, Sudha Rao +10
We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives. Our testbed…